|
train_distillation.py
|
[fix] dist cleanup
|
2026-01-02 22:25:55 +08:00 |
|
train_dpo.py
|
[fix] dist cleanup
|
2026-01-02 22:25:55 +08:00 |
|
train_full_sft.py
|
[fix] dist cleanup
|
2026-01-02 22:25:55 +08:00 |
|
train_grpo.py
|
[fix] dist cleanup
|
2026-01-02 22:25:55 +08:00 |
|
train_lora.py
|
[fix] dist cleanup
|
2026-01-02 22:25:55 +08:00 |
|
train_ppo.py
|
[fix] dist cleanup
|
2026-01-02 22:25:55 +08:00 |
|
train_pretrain.py
|
[fix] dist cleanup
|
2026-01-02 22:25:55 +08:00 |
|
train_reason.py
|
[update] rename reason
|
2026-01-05 23:12:29 +08:00 |
|
train_spo.py
|
[fix] dist cleanup
|
2026-01-02 22:25:55 +08:00 |
|
train_tokenizer.py
|
[update] rename train tokenizer
|
2026-01-06 01:17:33 +08:00 |
|
trainer_utils.py
|
[feat] get params
|
2025-12-31 20:46:59 +08:00 |